███████╗██╗ ██╗██╗██╗ ██╗ ██████╗ █████╗ ███╗ ██╗██╗ ██╗
██╔════╝██║ ██╔╝██║██║ ██║ ██╔══██╗██╔══██╗████╗ ██║██║ ██╔╝
███████╗█████╔╝ ██║██║ ██║ ██████╔╝███████║██╔██╗ ██║█████╔╝
╚════██║██╔═██╗ ██║██║ ██║ ██╔══██╗██╔══██║██║╚██╗██║██╔═██╗
███████║██║ ██╗██║███████╗███████╗ ██║ ██║██║ ██║██║ ╚████║██║ ██╗
╚══════╝╚═╝ ╚═╝╚═╝╚══════╝╚══════╝ ╚═╝ ╚═╝╚═╝ ╚═╝╚═╝ ╚═══╝╚═╝ ╚═╝
Agent Skills 排行榜 · 关键词 + 语义搜索
| # | Skill | 仓库 | 描述 | 安装量 |
|---|---|---|---|---|
| 7951 | stealth-browser | changeflowhq/skills |
stealth-browser Invisible Chrome automation via CDP. Launches your real Chrome hidden, sends commands via Chrome DevTools Protocol. Sites see a normal browser - no detectable automation. macOS only. Uses AppleScript and open -g to hide Chrome. Memory Read ~/.claude/skills/stealth-browser/LEARNED.md at the start of every task. If it doesn't exist, create it with a Learned header. Capture learnings when you detect: Domain quirks: sites that need extra wait time, cookie dismissal, specific interac...
|
106 |
| 7952 | eve-fullstack-app-design | incept5/eve-skillpacks |
Full-Stack App Design on Eve Horizon Architect applications where the manifest is the blueprint, the platform handles infrastructure, and every design decision is intentional. When to Use Load this skill when: Designing a new application from scratch on Eve Migrating an existing app onto the platform Evaluating whether your current architecture uses Eve's capabilities well Planning service topology, database strategy, or deployment pipelines Deciding between managed and external services This sk...
|
106 |
| 7953 | angular-migration | sickn33/antigravity-awesome-skills |
Angular Migration Master AngularJS to Angular migration, including hybrid apps, component conversion, dependency injection changes, and routing migration. When to Use This Skill Migrating AngularJS (1.x) applications to Angular (2+) Running hybrid AngularJS/Angular applications Converting directives to components Modernizing dependency injection Migrating routing systems Updating to latest Angular versions Implementing Angular best practices Migration Strategies 1. Big Bang (Complete Rewrite) ...
|
106 |
| 7954 | web3-testing | sickn33/antigravity-awesome-skills |
Web3 Smart Contract Testing Master comprehensive testing strategies for smart contracts using Hardhat, Foundry, and advanced testing patterns. When to Use This Skill Writing unit tests for smart contracts Setting up integration test suites Performing gas optimization testing Fuzzing for edge cases Forking mainnet for realistic testing Automating test coverage reporting Verifying contracts on Etherscan Hardhat Testing Setup // hardhat.config.js require("@nomicfoundation/hardhat-toolbox"); requi...
|
106 |
| 7955 | design | rshankras/claude-code-apple-skills |
Design pages using the design_page and edit_page MCP tools. design_page creates AI-generated design variations that the user can preview and select. edit_page applies targeted changes directly to an existing Subframe page. Both produce designs the user can refine visually in the Subframe editor and then implement in code. Update the theme for the entire project using edit_theme . Don't write UI code directly. Subframe generates production-ready React/Tailwind code that matches the design system....
|
106 |
| 7956 | nextjs-code-review | giuseppe-trisciuoglio/developer-kit |
Next.js Code Review Overview This skill provides structured, comprehensive code review for Next.js applications built with the App Router. It evaluates code against Next.js best practices, React Server Component patterns, caching strategies, and production-readiness criteria. The review produces actionable findings categorized by severity (Critical, Warning, Suggestion) with concrete code examples for improvements. This skill delegates to the typescript-software-architect-review agent for deep a...
|
106 |
| 7957 | ios-device-screenshot | 0xbigboss/claude-code |
iOS Device Screenshot Take screenshots from physical iOS devices connected via USB using pymobiledevice3. Installation Install pymobiledevice3 using uv (recommended) uv tool install pymobiledevice3 Or with pipx pipx install pymobiledevice3 Prerequisites Physical iOS device connected via USB Developer Mode enabled on the device (Settings > Privacy & Security > Developer Mode) Device trusted - approve "Trust This Computer" prompt on device Usage For iOS 17+ (including iOS 26+) iOS 17+ requi...
|
106 |
| 7958 | redmine-issue-manager | api/git |
No SKILL.md available for this skill. View on GitHub
|
106 |
| 7959 | add-components-to-registry | tambo-ai/tambo |
Add Components to Registry Convert existing React components into Tambo-registered components that AI can render. Quick Start Point to a component file or folder /add-components-to-registry src/components/ProductCard.tsx /add-components-to-registry src/components/cards/ Workflow Read component(s) - Analyze props, types, and purpose Generate Zod schema - Create propsSchema from prop types Write description - Help AI know when to use it Add to registry - Update lib/tambo.ts Step 1: Analyze Compon...
|
106 |
| 7960 | vsl-storyboard-writer | ncklrs/startup-os-skills |
Expert video sales letter and product marketing script writer specializing in high-converting video content that drives action. This skill bridges copywriting and video production, creating storyboard scripts ready for motion design implementation. Philosophy Great video sales scripts combine three elements: - Sales psychology — Understanding what drives decisions at each stage - Visual storytelling — Every scene advances both narrative and conversion - Production readiness — Scripts that ...
|
106 |
| 7961 | ln-500-story-quality-gate | levnikolaevich/claude-code-skills |
Paths: File paths ( shared/ , references/ , ../ln-* ) are relative to skills repo root. If not found at CWD, locate this SKILL.md directory and go up one level for repo root. Story Quality Gate Thin orchestrator that coordinates quality checks and test planning, then determines final Story verdict. Inputs Input Required Source Description storyId Yes args, git branch, kanban, user Story to process Resolution: Story Resolution Chain. Status filter: To Review Purpose & Scope Invoke ln-510-quality-...
|
106 |
| 7962 | changelog-automation | sickn33/antigravity-awesome-skills |
Changelog Automation Patterns and tools for automating changelog generation, release notes, and version management following industry standards. Use this skill when Setting up automated changelog generation Implementing conventional commits Creating release note workflows Standardizing commit message formats Managing semantic versioning Do not use this skill when The project has no release process or versioning You only need a one-time manual release note Commit history is unavailable or unrelia...
|
106 |
| 7963 | skill-development | aiskillstore/marketplace |
Skill Development for Claude Code Plugins This skill provides guidance for creating effective skills for Claude Code plugins. About Skills Skills are modular, self-contained packages that extend Claude's capabilities by providing specialized knowledge, workflows, and tools. Think of them as "onboarding guides" for specific domains or tasks—they transform Claude from a general-purpose agent into a specialized agent equipped with procedural knowledge that no model can fully possess. What Skills Pr...
|
106 |
| 7964 | tooluniverse-gwas-snp-interpretation | mims-harvard/tooluniverse |
GWAS SNP Interpretation Skill Overview Interpret genetic variants (SNPs) from GWAS studies by aggregating evidence from multiple sources to provide comprehensive clinical and biological context. Use Cases: "Interpret rs7903146" (TCF7L2 diabetes variant) "What diseases is rs429358 associated with?" (APOE Alzheimer's variant) "Clinical significance of rs1801133" (MTHFR variant) "Is rs12913832 in any fine-mapped loci?" (Eye color variant) What It Does The skill provides a comprehensive interpretati...
|
106 |
| 7965 | flutter-bloc-development | abdelhakrazi/flutter-bloc-clean-architecture-skill |
Flutter BLoC Development This skill enforces BLoC state management, strict layer separation, and mandatory use of design system constants for all Flutter development in this codebase. Decision Tree: Choosing Your Approach User task → What are they building? │ ├─ New screen/feature → Full stack implementation: │ 1. Define BLoC (events, states, bloc) │ 2. Create/update data layer (repository, datasource) │ 3. Build UI with design system │ ├─ New widget only → Pr...
|
106 |
| 7966 | claude-ally-health | sickn33/antigravity-awesome-skills |
Claude Ally Health Overview A health assistant skill for medical information analysis, symptom tracking, and wellness guidance. When to Use This Skill Use this skill when you need to work with a health assistant skill for medical information analysis, symptom tracking, and wellness guidance.. Instructions This skill provides guidance and patterns for a health assistant skill for medical information analysis, symptom tracking, and wellness guidance.. For more information, see the source repositor...
|
106 |
| 7967 | customer-success-manager | alirezarezvani/claude-skills |
Customer Success Manager Production-grade customer success analytics with multi-dimensional health scoring, churn risk prediction, and expansion opportunity identification. Three Python CLI tools provide deterministic, repeatable analysis using standard library only -- no external dependencies, no API calls, no ML models. Table of Contents Capabilities Input Requirements Output Formats How to Use Scripts Reference Guides Templates Best Practices Limitations Capabilities Customer Health Scoring :...
|
106 |
| 7968 | bun-file-io | anomalyco/opencode |
Use this when Editing file I/O or scans in packages/opencode Handling directory operations or external tools Bun file APIs (from Bun docs) Bun.file(path) is lazy; call text, json, stream, arrayBuffer, bytes, exists to read. Metadata: file.size, file.type, file.name. Bun.write(dest, input) writes strings, buffers, Blobs, Responses, or files. Bun.file(...).delete() deletes a file. file.writer() returns a FileSink for incremental writes. Bun.Glob + Array.fromAsync(glob.scan({ cwd, absolute, onlyFil...
|
106 |
| 7969 | byterover | junsuzuki1973/openclaw-skill-byterover |
ByteRover CLI - Context Engineering Platform ByteRover is a context engineering platform that lets you curate context for your coding agents—patterns, decisions, and learnings. It automatically syncs context across team members and eliminates manual markdown file management. Configuration API credentials are stored in ~/.clawdbot/byterover-config.json : { "apiKey" : "your_byterover_api_key_here" , "team" : "your_team_name" , "space" : "your_space_name" } Docker-Based Usage ByteRover CLI requires...
|
106 |
| 7970 | opencode-bridge | different-ai/openwork |
OpenWork communicates with OpenCode via three mechanisms: - CLI invocation: Spawn `opencode` with prompts and get JSON responses. - Database access: Read OpenCode's SQLite database for sessions and messages. - MCP bridge: Real-time bidirectional communication for streaming and permissions. CLI Invocation Non-interactive mode ``` opencode -p "your prompt" -f json -q ``` Returns JSON with the response content. Flags | `-p` | Prompt to execute | `-f` | Output format (`text`, `json`...
|
106 |
| 7971 | api-designer | charon-fan/agent-playbook |
API Designer Senior API architect with expertise in designing scalable, developer-friendly REST and GraphQL APIs with comprehensive OpenAPI specifications. Role Definition You are a senior API designer with 10+ years of experience creating intuitive, scalable API architectures. You specialize in REST design patterns, OpenAPI 3.1 specifications, GraphQL schemas, and creating APIs that developers love to use while ensuring performance, security, and maintainability. When to Use This Skill Desi...
|
106 |
| 7972 | sentry-flutter-sdk | getsentry/sentry-for-ai |
All Skills > SDK Setup > Flutter SDK Sentry Flutter SDK Opinionated wizard that scans your Flutter or Dart project and guides you through complete Sentry setup — error monitoring, tracing, session replay, logging, profiling, and ecosystem integrations. Invoke This Skill When User asks to "add Sentry to Flutter" or "set up Sentry" in a Flutter or Dart app User wants error monitoring, tracing, profiling, session replay, or logging in Flutter User mentions sentry_flutter , sentry_dart , mobile erro...
|
106 |
| 7973 | apple-ui-designer | heyman333/atelier-ui |
Apple UI Designer Role You are a senior Apple-style product designer who deeply understands iOS Human Interface Guidelines and modern Apple app design language. Your task is to redesign a mobile app UI to feel unmistakably Apple-like, iOS-forward, and native. Design Philosophy Native over custom Subtle over expressive Calm, confident, and human "Feels obvious" rather than "looks fancy" Avoid trendy UI gimmicks. Everything should feel inevitable and familiar to iOS users. Visual Style System...
|
106 |
| 7974 | java-architect | 404kidwiz/claude-supercode-skills |
Java Architect Senior Java architect with deep expertise in enterprise-grade Spring Boot applications, microservices architecture, and cloud-native development. Role Definition You are a senior Java architect with 15+ years of enterprise Java experience. You specialize in Spring Boot 3.x, Java 21 LTS, reactive programming with Project Reactor, and building scalable microservices. You apply Clean Architecture, SOLID principles, and production-ready patterns. When to Use This Skill Building Sp...
|
106 |
| 7975 | wechat-daily-report | advisorydz/wechat-daily-report-skill |
微信群聊日报生成 Skill 工作流程 1. 运行 analyze_chat.py 分析聊天记录 ↓ 2. AI 根据聊天文本生成内容 (ai_content.json) ↓ 3. 运行 generate_report.py 生成日报图片 (.png) ⚠️ 最终输出是 PNG 图片 ,不是 HTML。确保 --output 参数使用 .png 后缀。 使用步骤 1. 分析聊天记录 python scripts/analyze_chat.py < 聊天记录.json > --output-stats stats.json --output-text simplified_chat.txt 输出 : stats.json - 统计数据(话唠榜、熬夜冠军、词云等) simplified_chat.txt - 压缩格式聊天文本,供 AI 分析 格式: [时间段] 发言人A:内容 | 发言人B:内容/内容/内容 | 分隔不同发言人, / 分隔同一人连续消息 如消息量大(超过1800行),自动拆分为 simplified_chat_1.txt , simplified_chat_2.txt 等多...
|
106 |
| 7976 | elasticsearch-authn | elastic/agent-skills |
Elasticsearch Authentication Authenticate to an Elasticsearch cluster using any supported authentication realm that is already configured. This skill covers all built-in realms, credential verification, and the full API key lifecycle. For roles, users, role assignment, and role mappings, see the elasticsearch-authz skill. For detailed API endpoints, see references/api-reference.md . Deployment note: Not all realms are available on every deployment type. See Deployment Compatibility for self-mana...
|
106 |
| 7977 | motion-designer | ncklrs/startup-os-skills |
Motion Designer: Visual Animation Craft You are a motion designer creating expressive, purposeful movement. Apply Disney's 12 principles to craft animations that communicate and delight. The 12 Principles for Motion Design 1. Squash and Stretch The soul of organic movement. Compress on impact, elongate during speed. Preserve volume—wider means shorter. Use for characters, UI elements with personality, brand mascots. 2. Anticipation Wind-up before action. A button recoils before launching na...
|
106 |
| 7978 | webapp-testing | vudovn/antigravity-kit |
Web Application Testing To test local web applications, write native Python Playwright scripts. Helper Scripts Available : scripts/with_server.py - Manages server lifecycle (supports multiple servers) Always run scripts with --help first to see usage. DO NOT read the source until you try running the script first and find that a customized solution is abslutely necessary. These scripts can be very large and thus pollute your context window. They exist to be called directly as black-box scripts ra...
|
106 |
| 7979 | busybox-on-windows | davila7/claude-code-templates |
BusyBox is a single binary that implements many common Unix tools. Use this skill only on Windows. If you are on UNIX, then stop here. Run the following steps only if you cannot find a busybox.exe file in the same directory as this document is. These are PowerShell commands, if you have a classic cmd.exe terminal, then you must use powershell -Command "..." to run them. Print the type of CPU: Get-CimInstance -ClassName Win32_Processor | Select-Object Name, NumberOfCores, MaxClockSpeed Print t...
|
106 |
| 7980 | maestro-e2e | raphaelbarbosaqwerty/maestro-dev-skills |
When to use Use this skill whenever you are: Creating E2E, UI, or integration tests Testing login, registration, or navigation flows Handling permission dialogs (camera, location, notifications) Debugging test failures or exploring UI hierarchy Working with Maestro test files (.yaml) Captions When dealing with native permission dialogs, load the ./rules/permissions.md file for platform-specific information. When working with Flutter apps, load the ./rules/platforms/flutter.md file for Semantics ...
|
106 |
| 7981 | find-skills | nkchivas/openclaw-skill-find-skills |
Find Skills This skill helps you discover and install skills from the open agent skills ecosystem. When to Use This Skill Use this skill when the user: Asks "how do I do X" where X might be a common task with an existing skill Says "find a skill for X" or "is there a skill for X" Asks "can you do X" where X is a specialized capability Expresses interest in extending agent capabilities Wants to search for tools, templates, or workflows Mentions they wish they had help with a specific domain (desi...
|
106 |
| 7982 | wechat-channel | aaaaqwq/claude-code-skills |
微信 Channel 集成 将微信接入 OpenClaw,实现双向消息通道。 架构概述 ┌─────────────┐ ┌──────────────────┐ ┌─────────────┐ │ 微信用户 │ ←→ │ Wechaty Bridge │ ←→ │ OpenClaw │ │ (私聊/群聊) │ │ (PadLocal协议) │ │ Gateway │ └─────────────┘ └──────────────────┘ └─────────────┘ ↓ ┌──────────────────┐ │ 消息格式转换 │ │ - 文本/图片/文件 │ │ - @提及检测 │ │ - 群聊/私聊路由 │ └──────────────────┘ 核心组件 1. Wechaty Bridge (消息桥接服务) 独立运行的 Node.js 服务,负责: 微信登录(扫码) 消息收发 联系人/群组管理 与 OpenClaw Gateway 通信 2. OpenCl...
|
106 |
| 7983 | business-model-auditor | shipshitdev/library |
Business Model Auditor - Scale Stress Test Overview You are a business model auditor specializing in Alex Hormozi's scale and leverage principles. You help indie founders identify fatal flaws in their business model before they kill the business. Your job is to execute a stress test—not just advise—by exposing bottlenecks, calculating unit economics, and designing for scale. Hormozi's Core Principle: "A business model is only as good as its constraints. Can this scale without me?" When This A...
|
106 |
| 7984 | fal-workflow | fal-ai-community/skills |
fal.ai Workflow Generator Generate 100% working, production-ready fal.ai workflow JSON files . Workflows chain multiple AI models together for complex generation pipelines. References: Model Reference - Detailed model configurations Common Patterns - Reusable workflow patterns Code Examples - Code snippets and partial examples Troubleshooting Reference: Complete Workflows - Working JSON examples for debugging (use ONLY when user reports errors) Core Architecture Valid Node Types ⚠️ ONLY TWO VALI...
|
106 |
| 7985 | team-coordination | alinaqi/claude-bootstrap |
*Load with: base.md* Purpose: Enable multiple Claude Code sessions across a team to coordinate and work together without conflicts. Manages shared state, todo claiming, decision syncing, and session awareness. Core Philosophy ``` ┌─────────────────────────────────────────────────────────────────┐ │ TEAM CLAUDE CODE │ │ ───────────────────────────────────────────────────────────── │ │ Multiple devs, multiple Claude sessions, one codebase. ...
|
106 |
| 7986 | test-automator | charon-fan/agent-playbook |
Use this skill when Working on test automator tasks or workflows Needing guidance, best practices, or checklists for test automator Do not use this skill when The task is unrelated to test automator You need a different domain or tool outside this scope Instructions Clarify goals, constraints, and required inputs. Apply relevant best practices and validate outcomes. Provide actionable steps and verification. If detailed examples are required, open resources/implementation-playbook.md . You are a...
|
106 |
| 7987 | ai-ml-data-science | vasilyu1983/ai-agents-public |
Data Science Engineering Suite - Quick Reference This skill turns raw data and questions into validated, documented models ready for production: EDA workflows: Structured exploration with drift detection Feature engineering: Reproducible feature pipelines with leakage prevention and train/serve parity Model selection: Baselines first; strong tabular defaults; escalate complexity only when justified Evaluation & reporting: Slice analysis, uncertainty, model cards, production metrics SQL transfo...
|
106 |
| 7988 | widget-generator | f/prompts.chat |
Widget Generator Skill This skill guides creation of widget plugins for prompts.chat . Widgets are injected into prompt feeds to display promotional content, sponsor cards, or custom interactive components. Overview Widgets support two rendering modes: Standard prompt widget - Uses default PromptCard styling (like coderabbit.ts ) Custom render widget - Full custom React component (like book.tsx ) Prerequisites Before creating a widget, gather from the user: Parameter Required Description Widget ...
|
106 |
| 7989 | trigger-dev-tasks | triggerdotdev/trigger.dev |
Trigger.dev Task Expert You are an expert Trigger.dev developer specializing in building production-grade background job systems. Tasks deployed to Trigger.dev run in Node.js 21+ and use the @trigger.dev/sdk package. Critical Rules Always use @trigger.dev/sdk - Never use @trigger.dev/sdk/v3 or deprecated client.defineJob pattern Never use node-fetch - Use the built-in fetch function Export all tasks - Every task must be exported, including subtasks Never wrap wait/trigger calls in Promise.all ...
|
106 |
| 7990 | frontend-design-review | dauquangthanh/hanoi-rainbow |
This skill provides expert guidance for conducting thorough frontend design reviews, covering UI/UX design quality, design system consistency, accessibility compliance, and responsive design patterns. The skill helps identify design issues early in the development lifecycle, ensuring designs meet quality standards, accessibility requirements, and business objectives before implementation. Core Capabilities 1. UI/UX Design Quality Review - Visual design assessment (typography, color, spacing...
|
106 |
| 7991 | ctf-rev | cyberkaida/reverse-engineering-assistant |
You are a CTF reverse engineering solver. Your goal is to understand what a program does and extract the flag/key/password through systematic analysis. CTF reverse engineering is fundamentally about comprehension under constraints: - Limited time (competition pressure) - Unknown problem structure (what technique is being tested?) - Minimal documentation (that's the challenge!) - Goal-oriented (find the flag, not perfect understanding) Unlike malware analysis or vulnerability research, CTF ...
|
106 |
| 7992 | security-patterns | yonatangross/orchestkit |
Security Patterns Comprehensive security patterns for building hardened applications. Each category has individual rule files in rules/ loaded on-demand. Quick Reference Category Rules Impact When to Use Authentication 3 CRITICAL JWT tokens, OAuth 2.1/PKCE, RBAC/permissions Defense-in-Depth 2 CRITICAL Multi-layer security, zero-trust architecture Input Validation 3 HIGH Schema validation (Zod/Pydantic), output encoding, file uploads OWASP Top 10 2 CRITICAL Injection prevention, broken authentica...
|
106 |
| 7993 | builder | aj-geddes/claude-code-bmad-skills |
Builder Role: Builder Module specialist Function: Create custom agents, workflows, and templates for specialized domains Responsibilities Guide users in creating custom agents Generate workflow commands Create domain-specific templates Customize BMAD for specific use cases Extend BMAD functionality Core Principles User-Driven - Build what the user needs, not what exists Template-Based - Follow BMAD patterns and conventions Token-Optimized - Use helper references, avoid redundancy Functional -...
|
106 |
| 7994 | qa-expert | charon-fan/agent-playbook |
QA Expert Establish world-class QA testing processes for any software project using proven methodologies from Google Testing Standards and OWASP security best practices. When to Use This Skill Trigger this skill when: Setting up QA infrastructure for a new or existing project Writing standardized test cases (AAA pattern compliance) Executing comprehensive test plans with progress tracking Implementing security testing (OWASP Top 10) Filing bugs with proper severity classification (P0-P4) Gen...
|
106 |
| 7995 | nextjs-shadcn | laguagu/claude-code-nextjs-skills |
Build distinctive, production-grade interfaces that avoid generic "AI slop" aesthetics. Core Principles - Minimize noise - Icons communicate; excessive labels don't - No generic AI-UI - Avoid purple gradients, excessive shadows, predictable layouts - Context over decoration - Every element serves a purpose - Theme consistency - Use CSS variables from `globals.css`, never hardcode colors Quick Start ``` bunx --bun shadcn@latest create --preset "https://ui.shadcn.com/init?base=radix&style...
|
106 |
| 7996 | documentation-engineer | charon-fan/agent-playbook |
Documentation Engineer Purpose Specializes in creating, organizing, and maintaining comprehensive technical documentation systems that enhance developer productivity, knowledge transfer, and project understanding. Focuses on documentation as a first-class product that improves the entire development lifecycle. When to Use Building comprehensive technical documentation systems Creating API documentation and developer guides Implementing documentation-driven development workflows Organizing know...
|
106 |
| 7997 | evolink-image | evolinkai/image-generation-skill-for-openclaw |
Evolink Image — AI Image Generation & Editing Generate and edit AI images with 19 models including GPT Image 1.5, GPT-4o Image, Seedream, Qwen, WAN, and Gemini — all through one API. Image-focused view of evolink-media . Install the full skill for video and music too. After Installation When this skill is first loaded, greet the user: MCP tools + API key ready: "Hi! I'm your AI image studio — 19 models ready. What would you like to create?" MCP tools + no API key: "You'll need an EvoLink API key...
|
106 |
| 7998 | nsfc-research-foundation-writer | huangwb8/chineseresearchlatex |
见:[references/dod_checklist.md](https://github.com/huangwb8/chineseresearchlatex/blob/main/skills/nsfc-research-foundation-writer/references/dod_checklist.md) 常见问题与边缘情况 Q1: 项目目录中没有 `extraTex/` 目录怎么办? A: 本技能会自动尝试创建 `extraTex/` 目录。如果失败,请手动创建: ``` mkdir -p projects/NSFC_Young/extraTex ``` Q2: 我还没有写 `2.1 研究内容`,可以直接写 `3.1 研究基础` 吗? A: 不建议。`3.2 工作条件` 需要与 `2.1` 的关键任务对齐。建议先使用 `nsfc-research-content-writer` 完成 `2.1`。 Q3: 信息表中的某些内容我不方便公开怎么办? A: 可以提供"可核验线索"而非完整内容。例如: - ❌ "我们在 Nature 上发表了论文 XXX...
|
106 |
| 7999 | generate-synthetic-data | hamelsmu/evals-skills |
Generate Synthetic Data Generate diverse, realistic test inputs that cover the failure space of an LLM pipeline. Prerequisites Before generating synthetic data, identify where the pipeline is likely to fail. Ask the user about known failure-prone areas, review existing user feedback, or form hypotheses from available traces. Dimensions (Step 1) must target anticipated failures, not arbitrary variation. Core Process Step 1: Define Dimensions Dimensions are axes of variation specific to your appli...
|
106 |
| 8000 | clanker | bankrbot/openclaw-skills |
Clanker SDK Deploy production-ready ERC20 tokens with built-in liquidity pools using the official Clanker TypeScript SDK. Overview Clanker is a token deployment protocol that creates ERC20 tokens with Uniswap V4 liquidity pools in a single transaction. The SDK provides a TypeScript interface for deploying tokens with advanced features like vesting, airdrops, and customizable reward distribution. Quick Start Installation npm install clanker-sdk viem or yarn add clanker-sdk viem or pnpm add clan...
|
106 |